A Semiparametric Method for Valuing Residential Location: Application to Automated Valuation

Abstract

This paper is motivated by automated valuation systems, which would benefit from an ability to estimate spatial variation in location value. It develops theory for the LRM, a semiparametric approach to estimating a location value surface. There are two parts to the LRM: 1) an OLS model to hold constant for interior square footage, land area, bathrooms, and other structural characteristics; and 2) a non-parametric smoother (local polynomial regression, LPR) which calculates location value as a function of latitude and longitude. Several methods are used to consistently estimate both parts of the model. The LRM was fit to geocoded hedonic sales data for six towns in the suburbs of Boston, Massachusetts. The estimates yield substantial, significant and plausible spatial patterns in location values. Using the LRM as an exploratory tool, local peaks and valleys in location value identified by the model are close to points identified by the tax assessor, and they are shown to add to the explanatory power of an OLS model. Out-of-sample MSE shows that the LRM with a first-degree polynomial (local linear smoothing) is somewhat better than polynomials of degree zero or degree two. Future applications might use degree zero (the well-known NW estimator) because this is available in popular commercial software. The optimized LRM reduces MSE from the OLS model by between 5% and 11% while adding information on statistically significant variations in location value. models

Keywords: land values, neighborhood house values, property tax assessment, automated valuation, local polynomial smoothing regression, nonparametric methods, semiparametric